© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13975
    Prev
    Next
    INDEX
    Explanations

    a variety of computer code terms, names of music or sports persons, and certain math terms.

    oai_token-act-pair · gemini-2.0-flash

    Ne-Yo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.79
    ########.
    -0.74
    tagHelperRunner
    -0.74
     protoimpl
    -0.73
    GraphicsUnit
    -0.71
    niająca
    -0.71
    WriteBarrier
    -0.69
     Normdatei
    -0.66
     invokingState
    -0.64
    OGND
    -0.63
    POSITIVE LOGITS
    es
    0.54
    表
    0.49
    kop
    0.48
    form
    0.48
    epi
    0.47
    τισ
    0.46
    inic
    0.45
    чак
    0.45
    IpAddress
    0.45
     Heeren
    0.45
    Activations Density 11.639%

    No Known Activations